← All skills
video-production-harness
95 / 100 · Low risk
Fine to try.
By gooseworks-ai/goose-skills (GitHub) · media · 1,319 stars · scanned at commit df82981
Full video production sequence with script review, actual ingredient choices, controlled generation, editing, evidence-based quality review, polish, captions and delivery. A host binding supplies project storage, authentic approvals, provider access and billing.
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
The author does not mention this.
Found in 18 places.
Show 15 more
- skills/video/video-production-harness/scripts/check_recipe.py, line 66
result = subprocess.run(["ffmpeg", "-hide_banner", "-nostats", *args], capture_output=True, text=True, timeout=timeout) - skills/video/video-production-harness/scripts/check_recipe.py, line 73
result = subprocess.run( - skills/video/video-production-harness/scripts/check_recipe.py, line 103
result = subprocess.run(["ffmpeg", "-v", "error", "-i", str(path), *pcm], capture_output=True, timeout=600, check=True) - skills/video/video-production-harness/scripts/check_recipe.py, line 169
run = subprocess.run(build["command"], shell=True, cwd=work, capture_output=True, text=True, timeout=timeout) - skills/video/video-production-harness/scripts/check_recipe.py, line 194
except (CheckError, OSError, KeyError, json.JSONDecodeError, subprocess.SubprocessError) as error: - skills/video/video-production-harness/scripts/final_measure.py, line 47
log = subprocess.run(["ffmpeg", "-nostdin", "-hide_banner", "-i", str(video), "-map", "0:v:0", - skills/video/video-production-harness/scripts/final_measure.py, line 67
probe = json.loads(subprocess.run(["ffprobe", "-v", "error", "-show_format", "-of", "json", str(path)], - skills/video/video-production-harness/scripts/qc_evidence.py, line 41
return subprocess.run(args, check=True, capture_output=True, text=True, timeout=timeout) - skills/video/video-production-harness/scripts/qc_evidence.py, line 132
except (subprocess.CalledProcessError, ValueError) as error: - skills/video/video-production-harness/scripts/qc_evidence.py, line 149
except subprocess.CalledProcessError as error: - skills/video/video-production-harness/scripts/reference_shots.py, line 38
log = subprocess.run(["ffmpeg", "-nostdin", "-hide_banner", "-i", str(video), "-map", "0:v:0", - skills/video/video-production-harness/scripts/reference_shots.py, line 50
raw = subprocess.run(["ffmpeg", "-nostdin", "-v", "error", "-ss", f"{at_s:.3f}", "-i", str(video), "-frames:v", "1", - skills/video/video-production-harness/scripts/reference_shots.py, line 103
data = json.loads(subprocess.run(["ffprobe", "-v", "error", "-show_streams", "-show_format", "-of", "json", str(video)], - skills/video/video-production-harness/scripts/reference_shots.py, line 139
subprocess.run(["ffmpeg", "-nostdin", "-v", "error", "-y", "-i", str(video), "-an", "-vf", f"fps={fps}", "-q:v", "2", - skills/video/video-production-harness/scripts/reference_shots.py, line 147
subprocess.run(["ffmpeg", "-nostdin", "-v", "error", "-y", "-ss", f"{(a + b) / 2:.3f}", "-i", str(video),
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'video-production-harness' ] || [ -L ~/.agents/skills/'video-production-harness' ]; then echo 'A skill folder named video-production-harness already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/gooseworks-ai/goose-skills' "$d" && git -C "$d" checkout --quiet 'df8298140d434a6363de0c265eb6af2e571d97a5' -- 'skills/video/video-production-harness' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/video/video-production-harness' ~/.agents/skills/'video-production-harness' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'video-production-harness' ~/.claude/skills/'video-production-harness' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for gooseworks-ai/goose-skills shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/gooseworks-ai/goose-skills/)
Score history
| Date | Version | Score |
|---|
| 2026-11-08 | df82981 | 95 |
| 2026-11-06 | df82981 | 95 |